A Method for Energy Consumption Prediction of Metallurgical Enterprises Based on Integrated Long Short-Term Memory Network

Abstract

The invention discloses a metallurgical enterprise energy consumption prediction method based on an integrated long-term and short-term memory network. The steps include: 1. collecting and preprocessing the energy consumption data of the metallurgical enterprise; 2. using the long-term short-term memory network to extract the depth of the energy consumption data of the metallurgical enterprise Learning features; 3 Construct a training set of energy consumption data of multiple metallurgical enterprises, and train support vector regression prediction models of energy consumption data of multiple metallurgical enterprises; 4 Use Jensen‑Shannon divergence to perform Select, the results of the selected support vector regression prediction model are fused using the adaptive linear normalization combination method. The invention can solve the problem that the robustness of the support vector regression prediction model of the energy consumption data of a single metallurgical enterprise is not strong, and improve the prediction effect of the energy consumption data of the metallurgical enterprise.

Description

technical field [0001] The invention relates to the technical field of energy consumption prediction of metallurgical enterprises, and mainly relates to a method for predicting energy consumption of metallurgical enterprises based on integrated long-term and short-term memory networks. Background technique [0002] Energy is an important material basis for the development of the national economy and an important guarantee for determining the future development of national science and technology, economic development and national defense construction. Energy conservation is a long-term strategic policy of my country's economic and social development, and it is also an extremely urgent task at present. However, with the development of the metallurgical industry, the problem of energy has become more and more serious, especially in the production of steel, copper and other products of metallurgical enterprises, if the production plan is unreasonable or the management methods ar...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, the present invention provides a metallurgical enterprise energy consumption prediction method based on integrated long-term short-term memory network, in order to fully consider the time characteristics of metallurgical enterprise energy consumption data and the performance of a single prediction model, through The integration method is used to solve the problem of the weak robustness of the support vector regression prediction model of the energy consumption data of a single metallurgical enterprise, so as to improve the prediction effect of the energy consumption data of the metallurgical enterprise

Images